Nearly Horizon-Free Offline Reinforcement Learning.

Tongzheng Ren Jialian Li Bo Dai Simon S. Du Sujay Sanghavi

Published in: NeurIPS (2021)

Keyphrases

reinforcement learning
function approximation
real time
learning algorithm
reinforcement learning algorithms
learning process
reinforcement learning methods

temporal difference learning
supervised learning
state space
robotic control
action selection
markov decision processes

machine learning
neural network
active learning
transfer learning
evolutionary algorithm
multi agent systems

search algorithm
temporal difference
information systems
search engine
multi agent reinforcement learning
relational reinforcement learning